Advancements in acne detection: application of the CenterNet network in smart dermatology.

Introduction: Acne detection is critical in dermatology, focusing on quality control of acne imagery, precise segmentation, and grading. Traditional research has been limited, typically concentrating on singular aspects of acne detection. Methods: We propose a multi-task acne detection method, employing a CenterNet-based training paradigm to develop an advanced detection system. This system collects acne images via smartphones and features multi-task capabilities for detecting image quality and identifying various acne types. It differentiates between noninflammatory acne, papules, pustules, nodules, and provides detailed delineation for cysts and post-acne scars. Results: The implementation of this multi-task learning-based framework in clinical diagnostics demonstrated an 83% accuracy in lesion categorization, surpassing ResNet18 models by 12%. Furthermore, it achieved a 76% precision in lesion stratification, outperforming dermatologists by 16%. Discussion: Our framework represents a advancement in acne detection, offering a comprehensive tool for classification, localization, counting, and precise segmentation. It not only enhances the accuracy of remote acne lesion identification by doctors but also clarifies grading logic and criteria, facilitating easier grading judgments.

Correction: Therapeutic effects of a walnut-derived peptide on NLRP3 inflammasome activation, synaptic plasticity, and cognitive dysfunction in T2DM mice.

Correction for 'Therapeutic effects of a walnut-derived peptide on NLRP3 inflammasome activation, synaptic plasticity, and cognitive dysfunction in T2DM mice' by Yanru Li et al., Food Funct., 2024, 15, 2295-2313, https://doi.org/10.1039/D3FO05076A.

[Correlation of nutritional status with clinical characteristics and lung function in children with cystic fibrosis]. / å›Šæ€§çº¤ç»´åŒ–å„¿ç«¥è¥å »çŠ¶å†µä¸Žä¸´åºŠç‰¹å¾å’Œè‚ºåŠŸèƒ½çš„ç›¸å ³æ€§åˆ†æž.

OBJECTIVES: To investigate the nutritional status of children with cystic fibrosis (CF) and understand the correlation between malnutrition and clinical characteristics as well as lung function. METHODS: A retrospective analysis was performed on clinical data of CF children admitted from January 2016 to June 2023. Clinical characteristics of CF children with different nutritional statuses were compared, and the correlation between malnutrition and lung function was analyzed. RESULTS: A total of 52 CF children were included, comprising 25 boys (48%) and 27 girls (52%), aged between 7 months and 17 years. Respiratory symptoms were the predominant clinical manifestations (96%, 50/52). The prevalence of malnutrition was 65% (34/52), with moderate/severe malnutrition being the most common (65%, 22/34). The malnutrition group had a longer duration of illness, higher proportion of digestive system symptoms, and lower levels of serum albumin (P<0.05). Pulmonary function parameters, including forced expiratory volume in one second as a percentage of the predicted value, ratio of forced expiratory volume in one second to forced vital capacity, forced expiratory flow at 25% of forced vital capacity exhaled, forced expiratory flow at 50% of forced vital capacity exhaled, forced expiratory flow at 75% of forced vital capacity exhaled, and maximum mid-expiratory flow as a percentage of the predicted value, were lower in the malnutrition group compared to the normal nutrition group (P<0.05). Correlation analysis showed body mass index Z-score was positively correlated with the above six pulmonary function parameters (P<0.05). CONCLUSIONS: The prevalence of malnutrition is high in CF children and is associated with decreased lung function. CF children with higher body mass index have better lung function. Therefore, screening and evaluation of nutritional status as well as appropriate nutritional intervention should be emphasized in CF children.

Toward High-Performance Hydrogenation at Room Temperature Through Tailoring Nickel Catalysts Stable in Aqueous Solution.

The development of highly active, reusable catalysts for aqueous-phase reactions is challenging. Herein, metallic nickel is encapsulated in a nitrogen-doped carbon-silica composite (SiO2@Ni@NC) as a catalyst for the selective hydrogenation of vanillin in aqueous media. The constructed catalyst achieved 99.8% vanillin conversion and 100% 4-hydroxymethyl-2-methoxyphenol selectivity at room temperature. Based on combined scanning transmission electron microscopy, X-ray photoelectron spectroscopy, and Raman analyses, the satisfactory catalytic performance is attributed to the composite structure consisting of an active metal, carbon, and silica. The hydrophilic silica core promoted dispersion of the catalyst in aqueous media. Moreover, the external hydrophobic NC layer has multiple functions, including preventing oxidation or leaching of the internal metal, acting as a reducing agent to reduce the internal metal, regulating the active-site microenvironment by enriching the concentrations of H2 and organic reactants, and modifying the electronic structure of the active metal via metal-support interactions. Density functional theory calculations indicated that NC facilitates vanillin adsorption and hydrogen dissociation to promote aqueous-phase hydrogenation. This study provides an efficient strategy for constructing encapsulated Ni-based amphiphilic catalysts to upgrade biomass-derived compounds.

Associations of dichlorophenols, trichlorophenols, and ortho-phenylphenol with the risk and prognosis of diabetes and prediabetes: A population-based study.

2,4-dichlorophenol (2,4-DCP), 2,5-DCP, 2,4,5-trichlorophenol (2,4,5-TCP), 2,4,6-TCP, and ortho-phenylphenol (OPP) are widely present in the environment. However, their associations with risk and prognosis of diabetes and prediabetes remains unclear. We investigated the associations of these five phenols with the risk of diabetes and prediabetes, and with all-cause and cardiovascular disease (CVD) mortality, in adults with diabetes or prediabetes (n=6419). Information on diabetes and prediabetes indicators, and mortality data was collected from the National Health and Nutrition Examination Survey. Logistic and Cox regression models were used to explore the associations of the five phenols with risk and prognosis of diabetes and prediabetes. Participants in the highest urinary 2,4-DCP and 2,5-DCP tertiles had higher odds of diabetes [adjusted odds ratio (aOR), 1.34, 95 % confidence interval (CI): 1.10, 1.62; aOR, 1.29, 95 % CI: 1.07, 1.56, respectively] than those in the lowest tertiles. Participants with urinary OPP concentrations above the limit of detection (LOD), but below median had an aOR of 1.25 (95 % CI: 1.08, 1.46) for prediabetes compared to those with concentrations below the LOD. In adults with diabetes, the highest 2,4-DCP and 2,5-DCP tertiles were associated with all-cause mortality [adjusted hazard ratio (aHR), 1.49; 95 % CI: 1.08, 2.06; aHR, 1.49; 95 % CI: 1.08, 2.05, respectively] and CVD mortality (aHR, 2.58; 95 % CI: 1.33, 4.97; aHR, 1.96; 95 % CI: 1.06, 3.60, respectively) compared with the lowest tertiles. Compared with 2,4,5-TCP concentrations below the LOD, those above median were associated with all-cause mortality (aHR: 1.75; 95 % CI: 1.24, 2.48) and CVD mortality (aHR: 2.34; 95 % CI: 1.19, 4.63) in adults with prediabetes. Furthermore, the associations between these phenols and mortality were strengthened in some subgroups. Environmental exposure to 2,4-DCP, 2,5-DCP, 2,4,5-TCP, and OPP increases the risk or adverse prognosis of diabetes or prediabetes in adults in the US. Further studies are required to confirm these findings.

A Synthesis of α-Alkyl Cycloenones by Pd-Catalyzed Suzuki-Miyaura Coupling with Cyclic Morita-Baylis-Hillman Adducts.

We herein disclose a Pd-catalyzed Suzuki-Miyaura coupling of cyclic Morita-Baylis-Hillman adducts with organoboronic acids under mild conditions, which allows for a rapid access to diverse α-alkyl substituted cycloenones. The advantage of this method resides in the employment of functionalized allyl alcohols as the unprecedented electrophilic partners in the absence of external activators.

DFSNet: A 3D Point Cloud Segmentation Network toward Trees Detection in an Orchard Scene.

In order to guide orchard management robots to realize some tasks in orchard production such as autonomic navigation and precision spraying, this research proposed a deep-learning network called dynamic fusion segmentation network (DFSNet). The network contains a local feature aggregation (LFA) layer and a dynamic fusion segmentation architecture. The LFA layer uses the positional encoders for initial transforming embedding, and progressively aggregates local patterns via the multi-stage hierarchy. The fusion segmentation module (Fus-Seg) can format point tags by learning a multi-embedding space, and the generated tags can further mine the point cloud features. At the experimental stage, significant segmentation results of the DFSNet were demonstrated on the dataset of orchard fields, achieving an accuracy rate of 89.43% and an mIoU rate of 74.05%. DFSNet outperforms other semantic segmentation networks, such as PointNet, PointNet++, D-PointNet++, DGCNN, and Point-NN, with improved accuracies over them by 11.73%, 3.76%, 2.36%, and 2.74%, respectively, and improved mIoUs over the these networks by 28.19%, 9.89%, 6.33%, 9.89, and 24.69%, respectively, on the all-scale dataset (simple-scale dataset + complex-scale dataset). The proposed DFSNet can capture more information from orchard scene point clouds and provide more accurate point cloud segmentation results, which are beneficial to the management of orchards.

Prone position in the mechanical ventilation of acute respiratory distress syndrome children: a systematic review and meta-analysis.

Background: Prone position has been well recognized for the treatment of adult acute respiratory distress syndrome (ARDS). We aimed to evaluate the role of prone position in the mechanical ventilation in children with ARDS, to provide evidence to the treatment and care of children with ARDS. Methods: We searched the Pubmed et al. databases by computer until January 23, 2024 for randomized controlled trials (RCTs) on the role of prone position in the mechanical ventilation in children with ARDS. We evaluated the quality of included studies according to the quality evaluation criteria recommended by the Cochrane library. RevMan 5.3 software was used for meta-analysis. Results: 7 RCTs involving 433 children with ARDS were included. Meta-analysis indicated that prone position is beneficial to improve the arterial oxygenation pressure [MD = 4.27 mmHg, 95% CI (3.49, 5.06)], PaO2/FiO2 [MD = 26.97, 95% CI (19.17, 34.77)], reduced the oxygenation index [MD = -3.52, 95% CI (-5.41, -1.64)], mean airway pressure [MD = -1.91 cmH2O, 95% CI (-2.27, -1.55)] and mortality [OR = 0.33, 95% CI (0.15, 0.73), all P < 0.05]. There were no statistical differences in the duration of mechanical ventilation between the prone position group and control group [MD = -17.01, 97.27, 95% CI (-38.28, 4.26), P = 0.12]. Egger test results showed that no significant publication bias was found (all P > 0.05). Conclusions: Prone position ventilation has obvious advantages in improving oxygenation, but there is no significant improvement in the time of mechanical ventilation in the treatment of children with ARDS. In the future, more large-sample, high-quality RCTs are still needed to further analyze the role of prone position in the mechanical ventilation in children with ARDS.

Effect of bi-enzyme hydrolysis on the properties and composition of hydrolysates of Manchurian walnut dreg protein.

Walnut dreg (WD) active peptides are an important source of dietary antioxidants; however, the products of conventional hydrolysis have limited industrial output owing to poor flavour and low bioactivity. To this end, in this study, we aimed to employ bvLAP, an aminopeptidase previously identified in our research, as well as commercially available Alcalase for bi-enzyme digestion. The flavour, antioxidant activity, and structures of products resulting from various digestion methods were compared. The results showed that the bi-enzyme digestion products had enhanced antioxidant activity, increased ß-sheet content, and reduced bitterness intensity from 9.65 to 6.93. Moreover, bi-enzyme hydrolysates showed a more diverse amino acid composition containing 1640 peptides with distinct sequences. These results demonstrate that bi-enzyme hydrolysis could be a potential process for converting WD into functional food ingredients. Additionally, our results provide new concepts that can be applied in waste processing and high-value utilisation of WD.

Long-term outcomes of endoscopic resection for well-differentiated nonampullary duodenal neuroendocrine tumors.

BACKGROUND & AIMS: Nonampullary duodenal neuroendocrine tumors (NAD-NETs) are rare with limited evidence regarding endoscopic treatment. The study aimed to investigate the efficacy and safety of endoscopic resection of well-differentiated NAD-NETs and evaluate long-term outcomes, including local recurrence and metastasis. METHODS: A total of 78 patients with NAD-NETs who underwent endoscopic resection between January 2011 and August 2022 were included. The clinicopathologic characteristics and treatment outcomes were collected and analyzed. RESULTS: En bloc resection was achieved for 74 of the tumors (94.9%) and R0 resection was obtained in 68 of the tumors (87.2%). Univariate analysis identified tumors in the second part of the duodenum, tumor size ≥ 10 mm and muscularis propria invasion as risk factors for non-curative resection. Two patients with R1 resection (vertical margin involvement) and two patients with lymphovascular invasion underwent additional surgery. Four patients experienced adverse events (5.1%), including two cases of delayed bleeding and two cases of perforation, all successfully managed conservatively. During a median follow-up period of 62.6 months, recurrence and lymph node metastasis were only detected in one patient with R1 resection 3 months after the original procedure. CONCLUSION: Endoscopic resection is safe and effective and provides a favorable long-term outcome for patients with well-differentiated NAD-NETs without regional lymph node or distant metastasis.

Phytic acid promotes high glucose-mediated bone marrow mesenchymal stem cells osteogenesis via modulating circEIF4B that sponges miR-186-5p and complexes with IGF2BP3.

Diabetes-related hyperglycemia inhibits bone marrow mesenchymal stem cell (BMSC) function, thereby disrupting osteoblast capacity and bone regeneration. Dietary supplementation with phytic acid (PA), a natural inositol phosphate, has shown promise in preventing osteoporosis and diabetes-related complications. Emerging evidence has suggested that circular (circ)RNAs implicate in the regulation of bone diseases, but their specific regulatory roles in BMSC osteogenesis in hyperglycemic environments remain elucidated. In this study, in virto experiments demonstrated that PA treatment effectively improved the osteogenic capability of high glucose-mediated BMSCs. Differentially expressed circRNAs in PA-induced BMSCs were identified using circRNA microarray analysis. Here, our findings highlight an upregulation of circEIF4B expression in BMSCs stimulated with PA under a high-glucose microenvironment. Further investigations demonstrated that circEIF4B overexpression promoted high glucose-mediated BMSC osteogenesis. In contrast, circEIF4B knockdown exerted the opposite effect. Mechanistically, circEIF4B sequestered microRNA miR-186-5p and triggered osteogenesis enhancement in BMSCs by targeting FOXO1 directly. Furthermore, circEIF4B inhibited the ubiquitin-mediated degradation of IGF2BP3, thereby stabilizing ITGA5 mRNA and promoting BMSC osteogenic differentiation. In vivo experiments, circEIF4B inhibition attenuated the effectiveness of PA treatment in diabetic rats with cranial defects. Collectively, our study identifies PA as a novel positive regulator of BMSC osteogenic differentiation through the circEIF4B/miR-186-5p/FOXO1 and circEIF4B/IGF2BP3/ITGA5 axes, which offers a new strategy for treating high glucose-mediatedBMSCosteogenic dysfunction and delayed bone regeneration in diabetes.

Rapid generation of high-quality structure figures for publication with PyMOL-PUB.

MOTIVATION: The advancement of structural biology has increased the requirements for researchers to quickly and efficiently visualize molecular structures in silico. Meanwhile, it is also time-consuming for structural biologists to create publication-standard figures, as no useful tools can directly generate figures from structure data. Although manual editing can ensure that figures meet the standards required for publication, it requires a deep understanding of software operations and/or program call commands. Therefore, providing interfaces based on established software instead of manual editing becomes a significant necessity. RESULTS: We developed PyMOL-PUB, based on the original design of PyMOL, to effectively create publication-quality figures from molecular structure data. It provides functions including structural alignment methods, functional coloring schemes, conformation adjustments, and layout plotting strategies. These functions allow users to easily generate high-quality figures, demonstrate structural differences, illustrate inter-molecular interactions, and predict performances of biomacromolecules. AVAILABILITY AND IMPLEMENTATION: Our tool is publicly available at https://github.com/BGI-SynBio/PyMOL-PUB.

DNA Bloom Filter enables anti-contamination and file version control for DNA-based data storage.

DNA storage is one of the most promising ways for future information storage due to its high data storage density, durable storage time and low maintenance cost. However, errors are inevitable during synthesizing, storing and sequencing. Currently, many error correction algorithms have been developed to ensure accurate information retrieval, but they will decrease storage density or increase computing complexity. Here, we apply the Bloom Filter, a space-efficient probabilistic data structure, to DNA storage to achieve the anti-error, or anti-contamination function. This method only needs the original correct DNA sequences (referred to as target sequences) to produce a corresponding data structure, which will filter out almost all the incorrect sequences (referred to as non-target sequences) during sequencing data analysis. Experimental results demonstrate the universal and efficient filtering capabilities of our method. Furthermore, we employ the Counting Bloom Filter to achieve the file version control function, which significantly reduces synthesis costs when modifying DNA-form files. To achieve cost-efficient file version control function, a modified system based on yin-yang codec is developed.

The Pea Oligosaccharides Could Stimulate the In Vitro Proliferation of Beneficial Bacteria and Enhance Anti-Inflammatory Effects via the NF-κB Pathway.

The oligosaccharides extracted from the seeds of peas, specifically consisting of raffinose, stachyose, and verbascose, fall under the category of raffinose family oligosaccharides (RFOs). The effect of RFOs on intestinal microflora and the anti-inflammatory mechanism were investigated by in vitro fermentation and cell experiments. Firstly, mouse feces were fermented in vitro and different doses of RFOs (0~2%) were added to determine the changes in the representative bacterial community, PH, and short-chain fatty acids in the fermentation solution during the fermentation period. The probiotic index was used to evaluate the probiotic proliferation effect of RFOs and the optimal group was selected for 16S rRNA assay with blank group. Then, the effects of RFOs on the inflammatory response of macrophage RAW264.7 induced by LPS were studied. The activity of cells, the levels of NO, ROS, inflammatory factors, and the expression of NF-κB, p65, and iNOS proteins in related pathways were measured. The results demonstrated that RFOs exerted a stimulatory effect on the proliferation of beneficial bacteria while concurrently inhibiting the growth of harmful bacteria. Moreover, RFOs significantly enhanced the diversity of intestinal flora and reduced the ratio of Firmicutes-to-Bacteroides (F/B). Importantly, it was observed that RFOs effectively suppressed NO and ROS levels, as well as inflammatory cytokine release and expression of NF-κB, p65, and iNOS proteins. These findings highlight the potential of RFOs in promoting intestinal health and ameliorating intestinal inflammation.

Comparative skin histological and transcriptomic analysis of Rana kukunoris with two different skin colors.

This study compares the skin structures of Rana kukunoris with two different skin colors living in the same area of Haibei in the Northeastern Qinghai-Tibet Plateau. The skin thickness of the khaki R. kukunoris was significantly greater than that of the brown R. kukunoris (P < 0.01), and significantly more mucous and granular glands were present on the dorsal skin of the khaki frog (P < 0.05). Meanwhile, the melanocytes on the dorsal skin of the brown frog were significantly larger than those on the khaki one (P < 0.05). Morphological changes in the expansion and aggregation of melanocytes seemed to deepen the skin color of R. kukunoris. Moreover, transcriptome sequencing identified tyrosine metabolism, melanogenesis, and riboflavin metabolism as the main pathways involved in melanin formation and metabolism in brown R. kukunoris. TYR, MC1R was upregulated as the skin color of R. kukunoris was deepened and contributed to melanin production and metabolism. In contrast, the khaki frog had significantly more upregulated genes and metabolic pathways related to autoimmunity. The khaki frog appeared to defend against ultraviolet (UV) radiation-induced damage by secreting mucus and small molecular peptides, whereas the brown frog protected itself by distributing a large amount of melanin. Hence, the different skin colors of R. kukunoris might represent different adaptation strategies for survival in the intense UV radiation environment of the Qinghai-Tibet Plateau.

High plasticity of ribosomal DNA organization in budding yeast.

In eukaryotic genomes, rDNA generally resides as a highly repetitive and dynamic structure, making it difficult to study. Here, a synthetic rDNA array on chromosome III in budding yeast was constructed to serve as the sole source of rRNA. Utilizing the loxPsym site within each rDNA repeat and the Cre recombinase, we were able to reduce the copy number to as few as eight copies. Additionally, we constructed strains with two or three rDNA arrays and found that the presence of multiple arrays did not affect the formation of a single nucleolus. Although alteration of the position and number of rDNA arrays did impact the three-dimensional genome structure, the additional rDNA arrays had no deleterious influence on cell growth or transcriptomes. Overall, this study sheds light on the high plasticity of rDNA organization and opens up opportunities for future rDNA engineering.

Therapeutic effects of a walnut-derived peptide on NLRP3 inflammasome activation, synaptic plasticity, and cognitive dysfunction in T2DM mice.

NLRP3 inflammasome activation plays a key role in the development of diabetes-induced cognitive impairment. However, strategies to inhibit NLRP3 inflammasome activation remain elusive. Herein, we evaluated the impact of a walnut-derived peptide, TWLPLPR (TW-7), on cognitive impairment in high-fat diet/streptozotocin-induced type 2 diabetes mellitus (T2DM) mice and explored its underlying mechanisms in high glucose-induced HT-22 cells. In the Morris water maze test, TW-7 alleviated cognitive deficits in mice; this was confirmed at the level of synaptic structure and dendritic spine density in the mouse hippocampus using transmission electron microscopy and Golgi staining. TW-7 increased the expression of synaptic plasticity-related proteins and suppressed the NEK7/NLRP3 inflammatory pathway, as determined by western blotting and immunofluorescence analysis. The mechanism of action of TW-7 was verified in an HT-22 cell model of high glucose-induced insulin resistance. Collectively, TW-7 could regulate T2DM neuroinflammation and synaptic function-induced cognitive impairment by inhibiting NLRP3 inflammasome activation and improving synaptic plasticity.

Optimizing skin disease diagnosis: harnessing online community data with contrastive learning and clustering techniques.

Skin diseases pose significant challenges in China. Internet health forums offer a platform for millions of users to discuss skin diseases and share images for early intervention, leaving large amount of valuable dermatology images. However, data quality and annotation challenges limit the potential of these resources for developing diagnostic models. In this study, we proposed a deep-learning model that utilized unannotated dermatology images from diverse online sources. We adopted a contrastive learning approach to learn general representations from unlabeled images and fine-tuned the model on coarsely annotated images from Internet forums. Our model classified 22 common skin diseases. To improve annotation quality, we used a clustering method with a small set of standardized validation images. We tested the model on images collected by 33 experienced dermatologists from 15 tertiary hospitals and achieved a 45.05% top-1 accuracy, outperforming the published baseline model by 3%. Accuracy increased with additional validation images, reaching 49.64% with 50 images per category. Our model also demonstrated transferability to new tasks, such as detecting monkeypox, with a 61.76% top-1 accuracy using only 50 additional images in the training process. We also tested our model on benchmark datasets to show the generalization ability. Our findings highlight the potential of unannotated images from online forums for future dermatology applications and demonstrate the effectiveness of our model for early diagnosis and potential outbreak mitigation.

Novel combination of iron-carbon composite and Fenton oxidation processes for high-concentration antibiotic wastewater treatment.

The research presented herein explores the development of a novel iron-carbon composite, designed specifically for the improved treatment of high-concentration antibiotic wastewater. Employing a nitrogen-shielded thermal calcination approach, the investigation utilizes a blend of reductive iron powder, activated carbon, bentonite, copper powder, manganese dioxide, and ferric oxide to formulate an efficient iron-carbon composite. The oxygen exclusion process in iron-carbon particles results in distinctive electrochemical cells formation, markedly enhancing wastewater degradation efficiency. Iron-carbon micro-electrolysis not only boosts the biochemical degradability of concentrated antibiotic wastewater but also mitigates acute biological toxicity. In response to the increased Fe2+ levels found in micro-electrolysis wastewater, this research incorporates Fenton oxidation for advanced treatment of the micro-electrolysis byproducts. Through the synergistic application of iron-carbon micro-electrolysis and Fenton oxidation, this research accomplishes a significant decrease in the initial COD levels of high-concentration antibiotic wastewater, reducing them from 90,000 mg/L to about 30,000 mg/L, thus achieving an impressive removal efficiency of 66.9%. This integrated methodology effectively reduces the pollutant load, and the recycling of Fe2+ in the Fenton process additionally contributes to the reduction in both the volume and cost associated with solid waste treatment. This research underscores the considerable potential of the iron-carbon composite material in efficiently managing high-concentration antibiotic wastewater, thereby making a notable contribution to the field of environmental science.

Research on evaluation of university education informatization level based on clustering technique.

Today, the utilization of Information Technology tools is considered an inevitable path in the education system. In this regard, assessing the effective integration of Information Technology tools in the educational system holds significant importance. This process can be automated using artificial intelligence techniques, which are the subject of the current study. In this research, initially, a set of 14 indicators related to levels of Education Informatization (EI) in higher education is introduced. Subsequently, a clustering-based strategy is proposed to rank the indicators and determine an optimal subset of these features. Based on this framework, it is demonstrated that using 11 indicators related to educational behaviors can achieve the highest accuracy in evaluating EI levels. The proposed approach employs a group of Support Vector Machines (SVMs) for EI level assessment, where classifier hyperparameters are tuned using reinforcement learning strategy. The performance of the proposed method is evaluated on real-world data and compared with previous works. The results indicate that the proposed method can assess EI levels in universities with an average accuracy of 93.64 %, outperforming compared methods by at least 4.09 %.